U-Net-Based Adaptive Subtraction Using Three Frequency Bands of Simulated Multiples for Their Suppression

Effectively suppressing seismic multiples relies heavily on the crucial task of adaptively subtracting the simulated multiples from the initial recorded data. By executing adaptive subtraction within the nonlinear regression (non-LR) framework, the U-net method (UNetM) has shown superior capability in mitigating the intricate disparities between the simulated and actual multiples when compared with the LR method. The low-, medium-, and high-frequency bands of simulated multiples have been used to effectively address frequency-dependent inconsistencies in the LR method. To further improve multiple suppression accuracy, three frequency bands (TFBs) of simulated multiples are used as three channels of the U-net input, which are matched with the initial recorded data during self-supervised training in this letter. Compared with the LR method inputting simulated multiples alone, the LR method inputting TFBs of simulated multiples, and the UNetM inputting simulated multiples alone, the proposed UNetM inputting TFBs of simulated multiples improves the signal-to-noise ratio (SNR) by 4.41, 2.07, and 1.99 in the synthetic data example and demonstrates superior improvement in preserving primaries and eliminating residual multiples in the field data example.